Densely Connected Convolutional Networks With Attention LSTM for Crowd Flows Prediction
Densely Connected Convolutional Networks With Attention LSTM for Crowd Flows Prediction
复制标题
用于人群流量预测的带有注意力 LSTM 的密集连接卷积网络
DOI：
10.1109/access.2019.2943890
复制
发表时间：
2019
期刊：
影响因子：
3.9
通讯作者：
Zhisong Pan
中科院分区：
文献类型：
--
作者：
Wei Li;Wei Tao;Junyang Qiu;Xin Liu;Xingyu Zhou;Zhisong Pan
随着城市化进程的加快，城市人群流量预测在交通管理、公共安全等领域具有重要意义。然而，由于原始数据中复杂的时空关系以及其他因素（如事件和天气）的影响，获得精确的预测具有挑战性。以前的一些工作尝试使用各种方法来解决这个问题，例如自回归积分移动平均，向量自回归和一些深度学习模型。然而，这些方法很少能全面捕捉时空相关性。在本文中，我们提出了一种新的时空预测模型，是基于密集连接的卷积网络和注意力长短期记忆（ST-DCNAL），同时预测的流入和流出的人群在一个特定的城市划分的区域。模型由空间部分、外部因素部分和时间部分组成。在空间部分，我们采用密集连接的卷积网络来提取不同层次的空间特征。外部因素部分利用全连接网络从辅助信息中提取特征。在最后一部分中，利用基于注意力的长短时记忆模块来捕获时间模式。为了证明所提出的模型的实用性和有效性，我们使用两个独立的现实世界的数据集，出租车在北京和自行车在纽约。实验结果表明，该模型的性能优于其他基线方法。
With the rapid progress of urbanization, predicting citywide crowd flows has become increasingly significant in many fields, such as traffic management and public security. However, influenced by the complex spatiotemporal relations in raw data and other factors, such as events and weather, obtaining a precise prediction is challenging. Some previous works attempted to address this problem using various ways, such as autoregressive integrated moving average, vector auto-regression and some deep learning models. However, seldom can these methods comprehensively capture the spatiotemporal correlations. In this paper, we propose a novel spatio-temporal prediction model that is based on densely connected convolutional networks and attention long short-term memory (ST-DCCNAL), to simultaneously predict the inflow and outflow of the crowds in regions divided within a specific city. The ST-DCCNAL model consists of three parts: spatial part, external factors part and temporal part. In the spatial part, we employ densely connected convolutional networks to extract spatial characteristics at different levels. The external factors part utilizes a fully connected network to extract features from auxiliary information. In the last part, an attention-based long short-term memory module is leveraged to capture the temporal pattern. To demonstrate the practicality and effectiveness of the proposed model, we evaluate it using two separate real-world datasets of taxis in Beijing and bikes in New York. The experimental results confirm that the performance of our model is better than that of other baseline methods.